© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104423
    Prev
    Next
    INDEX
    Explanations

    conditional checks and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utiliser
    -2.05
    tine
    -1.96
    Якщо
    -1.93
    ﾒ
    -1.88
     ordinateur
    -1.83
    蛧
    -1.81
     ruban
    -1.79
     layui
    -1.78
    Согласно
    -1.77
     behulp
    -1.77
    POSITIVE LOGITS
     decides
    1.88
     chose
    1.78
    1
    1.74
     contains
    1.71
     But
    1.70
     determines
    1.69
     exists
    1.68
     presents
    1.59
     came
    1.58
     showed
    1.58
    Activations Density 0.012%

    No Known Activations